i build alot of stuff with open source music models github.com/betweentwomidnigh…
Joined August 2023
- Tweets 3,223
- Following 274
- Followers 368
- Likes 5,890
854 Photos and videos
thecollabagepatch retweeted
Check out Awesome Stable Audio, a curated list of integrations and extensions for stable audio. If I missed anything or you build something cool, please submit a PR and I will add you!
github.com/Stability-AI/Awes…
7
7
56
3,096
thecollabagepatch retweeted
I' m so addicted to @GoogleMagenta RealTime 2 🎹
so to justify playing with it 24/7 I ported the real-time apps to @huggingface Spaces 🤗 (and ported the entire lib to pytorch/transformers too)
Play live in real time on
huggingface.co/magenta-commu…
1
15
102
34,051
almost
Jun 3
We Are Charlie Kirk ableton extension
2
3
296
62
thecollabagepatch retweeted
Jun 4
meet ORAM: a little agentic multi-track looper for wild generative audio exploration, created at @sonic_field 🦋
prompt, record, or upload a sound. loop it, shape it with quick FX, then summon a new sound from whatever is playing.
powered by @StabilityAI's increbile Stable Audio 3, fully local ✿
3
5
40
1,846
Insane week of releases this week! Feels we’re entering into the next chapter of neural synthesis. Less “here’s the full song you requested” more ppl building custom instruments. Leading the way are scientist-engineers busily shaving off milliseconds with cleverer algo design.
Really proud to share something we’ve been working on for a while: Magenta RealTime 2 (MTR2), a live music model that is highly interactive (MIDI, audio, text, lots of parameters) and low-latency (~200ms end-to-end), and runs locally on a MacBook!
6
14
118
6,688
i see ppl making chord generators with the
ableton extensions sdk
im making some everything generators with it
first up: stable audio 3
next up ace-step-1.5
Expand, reshape and hack Live with the free Extensions SDK, an experimental playground inside Live Suite – now in public beta. Link in comments.
6
15
117
31,804
some features of my vst might still be more powerful
but these extensions are gonna present some crazy UX
3
766
there's not enough neural networks doing ascii art
@thepatch_kev quote of the day: "honestly feel like as this gets dialed in it's gonna be the vibecore slop pipeline we both need"
1
1
5
420
the workflow has become a
choose-your-own-adventure at this point
can watch the full collab with stable audio 3 on yt ⬇️
May 26
using bpm, key, a locked seed
and multiple LoRa's
makes stable audio 3 feel like an instrument
1
2
14
1,535
full video - blending 4 loras into a song inside ableton
youtu.be/TR3IwXlscdE
i'll be doing a bunch of these as i train more loras and experiment
1
214
if i haven't been clear enough
the real unlock is loading up several of your own loras
that's when sa3 turns into a custom song builder.
@dadabots' underfit is the dankest way to train
them
github.com/dada-bots/underfi…
1
1
126
opus 4.8 is running a lot of unnecessary tool calls and then hallucinating about their outputs
it makes me wonder if this is that honesty they're talking about, and previous opus was doing this too and not telling me
358
May 27
stable audio 3 is most fun when you train a bunch of loras
i have a feeling this is easier/better than my vibed up dgx spark container
1
7
699
May 26
using bpm, key, a locked seed
and multiple LoRa's
makes stable audio 3 feel like an instrument
May 20
some ai music models are actually made with musicians in mind
stable audio 3 is a great example of that.
grateful to @zqevans and friends for the opportunity to get a jumpstart on integrating this into the DAW
it's going to be a very fun summer.
if you want to play with it in the pre-release of gary4juce v4...⬇️
2
3
71
8,578
May 26
can run it locally inside gary now with your own loras
lmk if anything's broken plz
github.com/betweentwomidnigh…
12
282
May 24
the hardest part of implementing ML interfaces for me is always
surfacing progress updates to the UI properly
1
3
348
thecollabagepatch retweeted
May 22
Can we transform offline audio diffusion into real-time streaming interactive instruments?
Yes!
Presenting Live Music Diffusion Models: a new paradigm for taking your favorite open models into live performance, right on your own laptop! 🎵🎵
🧵
9
29
162
13,304
May 22
in the name of research
we got an arduino uno q (4gb of ram) to run stable-audio-3-small-sfx
using a swap file, after 3 minutes, it actually worked lol
2
2
23
3,427
May 20
some ai music models are actually made with musicians in mind
stable audio 3 is a great example of that.
grateful to @zqevans and friends for the opportunity to get a jumpstart on integrating this into the DAW
it's going to be a very fun summer.
if you want to play with it in the pre-release of gary4juce v4...⬇️
May 20
Meet Stable Audio 3.0, the open-weight model family built for artistic experimentation.
This is our open invitation to experiment with generative audio. We believe the best innovations are still waiting to be built.
The 4-1-1 on 3.0:
📣 You own your outputs, and can distribute and commercialize them under the Stability AI Community License (up to $1 million in revenue).
🎵 New and improved capabilities include variable-length generation up to six minutes, and full song composition on portable devices, no GPU required.
✅ Trained on a fully licensed dataset.
🎨 You can customize the models on your own library with support for LoRa training, which we’ve documented for the first time.
More on the models 👇
3
21
172
33,379
May 20
i will be furiously adding features and LoRas for us all to blend,
and of course, a local backend will be added to gary4local this week for both pc and mac users
github.com/betweentwomidnigh…
1
4
543